Battery pack fault detection method and system and electric vehicle

Abstract

The invention relates to a battery pack fault detection method and system and an electric vehicle. The battery pack fault detection method and system and the electric vehicle are simple in structure and ingenious in design, and the safety performance of a battery pack can be effectively improved. The state of the battery pack can be comprehensively known by monitoring the total voltage, the monomer voltage, the temperature and the current in real time; by screening out the battery cells with abnormal temperature, voltage or current and then diagnosing and analyzing whether the abnormal battery cells are subjected to micro short circuit, the abnormal battery cells can be quickly identified, unnecessary inspection on normal battery cells is reduced, and the detection efficiency is improved; battery faults can be comprehensively detected through a physical model, machine learning, time sequence analysis, ICA testing and EIS testing, and the accuracy and reliability of detection are further improved; according to the method, the safety and reliability of the battery pack are improved, the intelligent level of the battery management system is enhanced, and better use experience is provided for a user of the electric vehicle.

Description

Technical Field

[0001] The present invention relates to the field of new energy battery technology, and more specifically, to a battery pack fault detection method, system and electric vehicle. Background Art

[0002] With the advancement of science and technology, people's environmental awareness has gradually increased. In order to better protect the environment and respond to the call for energy conservation and emission reduction, new energy vehicles are becoming more and more popular among the public. New energy vehicles are mainly powered by batteries, such as valve-port sealed lead-acid batteries, ternary lithium batteries and lithium iron phosphate batteries.

[0003] During use, the battery pack may have safety hazards caused by abnormality of a single cell. Such safety hazards caused by individual problems of the cell will lead to the deterioration of power battery performance and may also induce thermal runaway. In severe cases, the power battery will catch fire, burn, and explode. If electric vehicle fires occur frequently, it will undermine consumers' confidence in electric vehicles and hinder the development of the electric vehicle industry. Therefore, how to grasp the individual differences of the cells, nip power battery safety accidents in the bud, and avoid thermal runaway has become the focus of research.

[0004] As the battery pack is used for a long time, the micro short circuit of the single cell will gradually accumulate and expand the impact on the performance and safety of the battery pack with the use of the power battery, and eventually the battery pack will fail. The existing battery fault detection has certain uncertainty and hysteresis, and the error is large; therefore, it is necessary to develop a battery pack fault detection method, system and electric vehicle. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a battery pack fault detection method, system and electric vehicle in view of the above-mentioned defects of the prior art.

[0006] In the first aspect, the technical solution adopted by the present invention to solve the technical problem is: a battery pack fault detection method, which includes the following steps:

[0007] S10: Data collection: real-time monitoring and collection of the total voltage V_total of the battery pack, the voltage V_i of each battery cell, temperature and current data;

[0008] S20: Hierarchical diagnosis: Screen out cells with abnormal temperature, voltage or current, and then diagnose and analyze the abnormal cells to see if they have micro-short circuits;

[0009] S30: Fault Analysis: Use physical models to analyze the behavior of the battery and machine learning to identify complex patterns and anomalies that the model cannot capture; and use time series analysis to track changes in battery performance over time, combining ICA and EIS data to identify performance degradation trends and potential signs of failure to improve the accuracy of fault detection.

[0010] In the battery pack fault detection method of the present invention, in step S20, the method for screening out cells with abnormal temperature, voltage or current is as follows:

[0011] Use a temperature detector to preliminarily screen the battery cells. If the temperature is higher or lower than the normal temperature threshold, it is an abnormal battery cell with abnormal temperature;

[0012] Calculate the difference between the total voltage V_total of the battery pack and the sum of the voltages V_i of all cells based on the collected data, i.e. |V_total-ΣV_i|, and use the diagnostic algorithm to analyze the voltage data to determine whether there is a voltage fault. If a fault occurs, it is an abnormal cell.

[0013] The BMS is used to monitor the current of each battery cell in real time and compare the current of each battery cell with the normal current threshold. If the current of the battery cell exceeds the normal threshold, the BMS will mark it as abnormal.

[0014] The battery pack fault detection method described in the present invention, wherein, in step S20, the screened abnormal battery cells are analyzed using EIS, ICA or ECIS to determine whether a micro short circuit occurs in the abnormal battery cells. If a micro short circuit occurs, the BMS will trigger an alarm and limit the current of the abnormal battery cells, disconnect the faulty battery cells, or balance the current output of other battery cells in the battery pack.

[0015] The battery pack fault detection method of the present invention, wherein in step S10, the high voltage of the battery pack is reduced to a voltage range suitable for a microcontroller or an analog-to-digital converter by a voltage divider;

[0016] Connect the input of the voltage divider to the positive and negative terminals of the battery pack, and connect the output of the voltage divider to the input of the microcontroller or analog-to-digital converter to complete the connection;

[0017] After the microcontroller reads the divided voltage value through the analog-to-digital converter, it converts the read voltage value into the actual total voltage of the battery pack through a software algorithm, and then detects the total voltage of the battery pack.

[0018] The battery pack fault detection method of the present invention, wherein the voltage of each battery cell is measured by a battery cell monitoring module;

[0019] The positive and negative terminals of each battery cell are connected to the corresponding input terminals of the monitoring cell monitoring module, and the output of the cell monitoring module is usually connected to the microcontroller through a communication interface to complete the connection;

[0020] The microcontroller reads the voltage data of each battery cell from the battery cell monitoring module through the communication interface (I2C or SPI interface), and then detects the voltage of a single battery cell; at the same time, the battery cell monitoring module converts the analog voltage signal into a digital signal.

[0021] In a second aspect, the present invention further provides a battery pack fault detection system, which includes:

[0022] Data acquisition module, real-time monitoring and acquisition of the total voltage V_total of the battery pack, the voltage V_i of each battery cell, temperature and current data;

[0023] The hierarchical diagnosis module screens out cells with abnormal temperature, voltage or current, and then diagnoses and analyzes the abnormal cells to see if they have a micro short circuit.

[0024] The fault analysis module uses a combination of physical models, machine learning, time series analysis, ICA, and EIS data to deeply analyze battery behavior, identify complex patterns and anomalies, track performance changes, and identify signs of failure.

[0025] The raw data collected by the data acquisition module is transmitted to the hierarchical diagnosis module; the abnormal data and diagnosis results screened by the hierarchical diagnosis module are further transmitted to the fault analysis module; the physical model, machine learning, time series analysis, ICA and EIS data are each used as a sub-module of the fault analysis module;

[0026] The machine learning module uses features extracted from physical models and raw data to identify complex patterns and anomalies; the time series analysis module tracks the changing trends of battery performance over time; and the ICA and EIS data modules provide electrochemical property analysis to identify performance degradation trends and signs of failure.

[0027] A battery pack fault detection system described in the present invention also includes a feedback module for feeding back the output data of the fault analysis module to the hierarchical diagnosis module to optimize the screening conditions; and the results of the fault analysis module can also be used to update the parameters of the data acquisition module.

[0028] In a third aspect, the present invention further provides an electric vehicle, which includes a battery pack; the battery pack adopts any of the battery pack fault detection methods described above to perform fault detection.

[0029] The beneficial effects of the present invention are as follows: the battery pack fault detection method, system and electric vehicle have a simple structure and ingenious design, and can effectively improve the safety performance of the battery pack; by real-time monitoring of the total voltage, single cell voltage, temperature and current, the state of the battery pack can be fully understood; by screening out battery cells with abnormal temperature, voltage or current, and then diagnosing and analyzing the abnormal battery cells to see whether a micro-short circuit has occurred, the abnormal battery cells can be quickly identified, unnecessary inspections of normal battery cells are reduced, and detection efficiency is improved; battery faults can be fully detected through physical models, machine learning, time series analysis, ICA testing and EIS testing, further improving the accuracy and reliability of detection; this method not only improves the safety and reliability of the battery pack, but also enhances the intelligence level of the battery management system, providing a better user experience for users of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be further described below in conjunction with the accompanying drawings and embodiments. The drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work:

[0031] Figure 1 is a flow chart of a battery pack fault detection method in Embodiment 1 of the present invention;

[0032] Figure 2 It is a principle block diagram of a battery pack fault detection system in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0033] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present invention and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0034] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0035] "Multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0036] Moreover, the terms "up, down, front, back, left, right, upper end, lower end, longitudinal" and the like indicating directions are all based on the posture and position of the device or equipment described in this solution during normal use.

[0037] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the following will be described clearly and completely in combination with the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are partial embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.

[0038] The electronic device protective case in the present invention is a shell specially designed for various electronic devices, used to protect the devices from collision, scratching, falling and dust, etc., and can effectively protect the appearance and internal components of the devices and extend the service life of the electronic devices. Electronic devices include but are not limited to mobile phones, tablet computers, laptop computers, readers, etc. Among them, the embodiments of the present invention are analyzed and explained by taking the mobile phone protective case as an example.

[0039] Embodiment 1:

[0040] A battery pack fault detection method according to a preferred embodiment of the present invention is as follows: Figure 1 As shown, the following steps are included:

[0041] S10: Data collection: Real-time monitoring and collection of the total voltage V_total of the battery pack, the voltage V_i of each battery cell, temperature and current data; through preliminary screening of temperature, voltage and current, potential problem batteries can be quickly identified.

[0042] The high voltage of the battery pack is reduced to a voltage range suitable for a microcontroller or an analog-to-digital converter through a voltage divider, thereby ensuring safe measurement of the high voltage and reducing the voltage to a range that the microcontroller or the analog-to-digital converter can handle.

[0043] Connect the input of the voltage divider to the positive and negative terminals of the battery pack, and connect the output of the voltage divider to the input of the microcontroller or analog-to-digital converter to complete the connection;

[0044] The microcontroller reads the voltage value after voltage division through the analog-to-digital converter, and then converts the read voltage value into the actual total voltage of the battery pack through the software algorithm, thereby detecting the total voltage of the battery pack. The combination of the microcontroller and the analog-to-digital converter realizes real-time data collection, making fault detection faster.

[0045] Furthermore, the voltage of each battery cell is measured by a battery cell monitoring module;

[0046] The positive and negative terminals of each battery cell are connected to the corresponding input terminals of the monitoring cell monitoring module, and the output of the cell monitoring module is usually connected to the microcontroller through a communication interface to complete the connection;

[0047] The microcontroller reads the voltage data of each battery cell from the battery monitoring module through the communication interface (I2C or SPI interface), and then detects the voltage of a single battery cell; at the same time, the battery monitoring module converts the analog voltage signal into a digital signal;

[0048] S20: Hierarchical diagnosis: Screen out cells with abnormal temperature, voltage or current, and then diagnose and analyze the abnormal cells to see if they have micro-short circuits;

[0049] Among them, the method of screening out cells with abnormal temperature, voltage or current is as follows:

[0050] Use a temperature detector to preliminarily screen the battery cells. If the temperature is higher or lower than the normal temperature threshold, it is an abnormal cell with abnormal temperature. Among them, the maximum temperature threshold for battery pack charging is approximately between 45°C and 50°C; the maximum temperature threshold for battery pack discharge may be slightly higher than the maximum temperature threshold for charging; the minimum temperature threshold for battery pack is usually between -20°C and 0°C. The purpose of setting temperature thresholds is to ensure that the battery operates within a safe and optimal operating temperature range, thereby ensuring the performance of the battery and extending its service life; if the battery pack exceeds the range of the normal temperature threshold corresponding to its situation under the response, it can be preliminarily judged as an abnormal cell;

[0051] Calculate the difference between the total voltage V_total of the battery pack and the sum of the voltages V_i of all cells based on the collected data, i.e. |V_total-ΣV_i|, and use the diagnostic algorithm to analyze the voltage data to determine whether there is a voltage fault. If a fault occurs, it is an abnormal cell.

[0052] The BMS monitors the current of each cell in real time and compares the current of each cell with the normal current threshold. If the current of the cell exceeds the normal threshold, the BMS will mark it as abnormal.

[0053] Furthermore, the screened abnormal cells are analyzed using EIS (electrochemical impedance spectroscopy), ICA (incremental capacity analysis) or ECIS (extended electrochemical impedance spectroscopy) to determine whether the abnormal cells have micro-short circuits. If micro-short circuits occur, the BMS will trigger an alarm and limit the current of the abnormal cells, disconnect the faulty cells, or balance the current output of other cells in the battery pack. Among them, if the voltage is close to zero or very low, and the battery pack is not connected to any load or charger, a short circuit appears on the surface; if the resistance value is much lower than the internal resistance of a normal battery, usually less than 10 milliohms, it indicates an internal short circuit; connect a known resistor at both ends of the battery pack and measure the current through the resistor. If the current is much larger than expected, this may indicate that the battery pack has a short circuit.

[0054] S30: Fault Analysis: Use physical models to analyze the behavior of the battery and machine learning to identify complex patterns and anomalies that the model cannot capture; and use time series analysis to track changes in battery performance over time, combining ICA and EIS data to identify performance degradation trends and potential signs of failure to improve the accuracy of fault detection.

[0055] Among them, the physical model in this embodiment is a battery mathematical model in the prior art, such as an equivalent circuit model, which is used to determine the physical and chemical properties of the battery; the parameters are optimized by minimizing the difference between the model prediction and the actual measurement of the physical model, and an independent test data set is used to verify the accuracy of the model to ensure that the model can reasonably predict the battery behavior.

[0056] By collecting the raw data of battery voltage, current and temperature, and selecting any machine learning algorithm such as random forest, support vector machine, neural network, etc., the labeled data set is trained to identify normal and abnormal behaviors.

[0057] The battery data is converted into a time series format through time series analysis to ensure the accuracy of the data's timestamp; the time series data is analyzed to identify the changing trend of battery performance over time; statistical methods (such as autocorrelation function, moving average, etc.) are then used to analyze the trend, and time series prediction models such as ARIMA, LSTM, etc. are established to predict future changes in battery performance.

[0058] Through EIS testing, the impedance data of the battery is collected and impedance features such as impedance modulus and phase angle are extracted from it; through ICA testing, the mixed signal is decomposed to identify independent electrochemical processes, and independent components are extracted from the ICA data, and their changes are analyzed. Then, the changes of EIS and ICA features over time are analyzed and the trend of performance degradation is analyzed and identified. Then, statistical or machine learning methods are used to identify potential signs of failure to improve the accuracy of fault detection. It is highly targeted and focuses on the micro-short circuit problem of abnormal batteries, which helps to accurately identify the cause of the fault;

[0059] The battery pack fault detection method, system and electric vehicle have a simple structure and ingenious design, and can effectively improve the safety performance of the battery pack; by real-time monitoring of the total voltage, single cell voltage, temperature and current, the state of the battery pack can be fully understood; by screening out battery cells with abnormal temperature, voltage or current, and then diagnosing and analyzing the abnormal battery cells to see whether a micro-short circuit has occurred, the abnormal battery cells can be quickly identified, unnecessary inspections of normal battery cells are reduced, and detection efficiency is improved; through physical models, machine learning, time series analysis, ICA testing and EIS testing, battery faults can be fully detected, further improving the accuracy and reliability of detection.

[0060] Embodiment 2

[0061] This embodiment provides a battery pack fault detection system. Figure 2 As shown, including:

[0062] The data acquisition module 11 monitors and collects the total voltage V_total of the battery pack, the voltage V_i of each battery cell, the temperature and current data in real time;

[0063] The hierarchical diagnosis module 12 selects cells with abnormal temperature, voltage or current, and then diagnoses and analyzes the abnormal cells to determine whether a micro short circuit has occurred.

[0064] Fault Analysis Module 13 uses a combination of physical models, machine learning, time series analysis, ICA, and EIS data to deeply analyze battery behavior, identify complex patterns and anomalies, track performance changes, and identify signs of failure.

[0065] The raw data collected by the data acquisition module 11 is transmitted to the hierarchical diagnosis module 12; the abnormal data and diagnosis results screened by the hierarchical diagnosis module 12 are further transmitted to the fault analysis module 13; the data of the physical model, machine learning, time series analysis, ICA test and EIS test are each used as a submodule of the fault analysis module 13;

[0066] The machine learning module uses features extracted from physical models and raw data to identify complex patterns and anomalies; the time series analysis module tracks the changing trends of battery performance over time; and the ICA and EIS data modules provide electrochemical property analysis to identify performance degradation trends and signs of failure.

[0067] Furthermore, it also includes a feedback module 14 for feeding back the output data of the fault analysis module 13 to the hierarchical diagnosis module 12 to optimize the screening conditions; and the result of the fault analysis module 13 can also be used to update the parameters of the data acquisition module 11.

[0068] The battery pack fault detection method, system and electric vehicle have a simple structure and ingenious design, and can effectively improve the safety performance of the battery pack; by real-time monitoring of the total voltage, single cell voltage, temperature and current, the state of the battery pack can be fully understood; by screening out battery cells with abnormal temperature, voltage or current, and then diagnosing and analyzing the abnormal battery cells to see whether a micro-short circuit has occurred, the abnormal battery cells can be quickly identified, unnecessary inspections of normal battery cells are reduced, and detection efficiency is improved; through physical models, machine learning, time series analysis, ICA testing and EIS testing, battery faults can be fully detected, further improving the accuracy and reliability of detection.

[0069] Embodiment 3

[0070] This embodiment provides an electric vehicle, which includes a battery pack; the battery pack is fault-detected using the battery pack fault detection method described in the first embodiment.

[0071] The battery pack fault detection method, system and electric vehicle have a simple structure and ingenious design, and can effectively improve the safety performance of the battery pack; by real-time monitoring of the total voltage, single cell voltage, temperature and current, the state of the battery pack can be fully understood; by screening out battery cells with abnormal temperature, voltage or current, and then diagnosing and analyzing the abnormal battery cells to see whether a micro-short circuit has occurred, the abnormal battery cells can be quickly identified, unnecessary inspections of normal battery cells are reduced, and detection efficiency is improved; through physical models, machine learning, time series analysis, ICA testing and EIS testing, battery faults can be fully detected, further improving the accuracy and reliability of detection.

[0072] This approach not only improves the safety and reliability of the battery pack, but also enhances the intelligence level of the battery management system, providing a better user experience for electric vehicle users.

[0073] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all these improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. A battery pack fault detection method, characterized in that: The following steps are involved: S10: Data collection: real-time monitoring and collection of the total voltage V_total of the battery pack, the voltage V_i of each battery cell, temperature and current data; S20: Hierarchical diagnosis: Screen out cells with abnormal temperature, voltage or current, and then diagnose and analyze the abnormal cells to see if they have micro-short circuits; S30: Fault Analysis: Use physical models to analyze the behavior of the battery and use machine learning to identify complex patterns and anomalies that the models cannot capture; Time series analysis is used to track changes in battery performance over time, combining ICA and EIS data to identify performance degradation trends and potential signs of failure to improve the accuracy of fault detection.

2. The battery pack fault detection method according to claim 1, characterized in that: In step S20, the method for screening out cells with abnormal temperature, voltage or current is as follows: Use a temperature detector to preliminarily screen the battery cells. If the temperature is higher or lower than the normal temperature threshold, it is an abnormal battery cell with abnormal temperature; Calculate the difference between the total voltage V_total of the battery pack and the sum of the voltages V_i of all cells based on the collected data, i.e. |V_total-ΣV_i|, and use the diagnostic algorithm to analyze the voltage data to determine whether there is a voltage fault. If a fault occurs, it is an abnormal cell. The BMS is used to monitor the current of each battery cell in real time and compare the current of each battery cell with the normal current threshold. If the current of the battery cell exceeds the normal threshold, the BMS will mark it as abnormal.

3. The battery pack fault detection method according to claim 1, characterized in that: In step S20, the screened abnormal cells are analyzed using EIS, ICA or ECIS to determine whether a micro short circuit occurs in the abnormal cells. If a micro short circuit occurs, the BMS will trigger an alarm and limit the current of the abnormal cells, disconnect the faulty cells, or balance the current output of other cells in the battery pack.

4. The battery pack fault detection method according to any one of claims 1 to 3, characterized in that: In step S10, the high voltage of the battery pack is reduced to a voltage range suitable for a microcontroller or an analog-to-digital converter through a voltage divider; Connect the input of the voltage divider to the positive and negative terminals of the battery pack, and connect the output of the voltage divider to the input of the microcontroller or analog-to-digital converter to complete the connection; After the microcontroller reads the divided voltage value through the analog-to-digital converter, it converts the read voltage value into the actual total voltage of the battery pack through a software algorithm, and then detects the total voltage of the battery pack.

5. The battery pack fault detection method according to claim 4, characterized in that: Measure the voltage of each battery cell through the battery cell monitoring module; The positive and negative terminals of each battery cell are connected to the corresponding input terminals of the monitoring cell monitoring module, and the output of the cell monitoring module is usually connected to the microcontroller through a communication interface to complete the connection; The microcontroller reads the voltage data of each battery cell from the battery cell monitoring module through the communication interface (I2C or SPI interface), and then detects the voltage of a single battery cell; at the same time, the battery cell monitoring module converts the analog voltage signal into a digital signal.

6. A battery pack fault detection system, characterized in that: include: Data acquisition module, real-time monitoring and acquisition of the total voltage V_total of the battery pack, the voltage V_i of each battery cell, temperature and current data; The hierarchical diagnosis module screens out cells with abnormal temperature, voltage or current, and then diagnoses and analyzes the abnormal cells to see if they have a micro short circuit. The fault analysis module uses a combination of physical models, machine learning, time series analysis, ICA, and EIS data to deeply analyze battery behavior, identify complex patterns and anomalies, track performance changes, and identify signs of failure. The raw data collected by the data acquisition module is transmitted to the hierarchical diagnosis module; the abnormal data and diagnosis results screened by the hierarchical diagnosis module are further transmitted to the fault analysis module; the physical model, machine learning, time series analysis, ICA and EIS data are each used as a sub-module of the fault analysis module; The machine learning module uses features extracted from physical models and raw data to identify complex patterns and anomalies; the time series analysis module tracks the changing trends of battery performance over time; and the ICA and EIS data modules provide electrochemical property analysis to identify performance degradation trends and signs of failure.

7. The fault detection system according to claim 6, characterized in that: It also includes a feedback module for feeding back the output data of the fault analysis module to the hierarchical diagnosis module to optimize the screening conditions; and the results of the fault analysis module can also be used to update the parameters of the data acquisition module.

8. An electric vehicle, characterized in that: Including a battery pack; the battery pack adopts the battery pack fault detection method as described in any one of claims 1-5 to perform fault detection.

Images